© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63771
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aland
    -0.31
    åģ¥åº·çļĦ
    -0.27
     ostr
    -0.27
    -ser
    -0.25
     Schön
    -0.25
    |^
    -0.25
     createContext
    -0.25
    æģ°å¥½
    -0.24
    |[
    -0.24
    wart
    -0.24
    POSITIVE LOGITS
    éĩijå¸ģ
    0.29
    iego
    0.26
     pos
    0.25
    积åĪĨ
    0.24
    ä¸ŃèĢĥ
    0.24
     mortality
    0.24
     mum
    0.24
    .require
    0.24
    å¾µ
    0.23
    ibu
    0.23
    Activations Density 7.079%

    No Known Activations

    This feature has no known activations.